Automatic static hand gesture recognition using ToF cameras

This paper presents an automatic algorithm for static hand gesture recognition relying on both depth and intensity information provided by a time-of-flight (ToF) camera. The combined depth and intensity information facilitates the segmentation process, even in the presence of a cluttered background (2 misses out of 450 images). Gesture classification is based on a decision tree using structural descriptions of partitioned contour segments. Classification was tested on 9 different gestures. The final mean recognition rate is satisfactory, of about 93.3%.